Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ur-grue/autopunk-media-skills --skill cinematic-shot-promptgit clone --depth 1 https://github.com/ur-grue/autopunk-media-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ur-grue/autopunk-media-skills/cinematic-shot-prompt)<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/cinematic-shot-prompt"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/cinematic-shot-prompt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ur-grue/autopunk-media-skills/cinematic-shot-prompt"><img src="https://agentmods.dev/badge/skills/ur-grue/autopunk-media-skills/cinematic-shot-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.01814 |
| Opus 5 | $0.00026 | $0.00907 |
| Sonnet 5 | $0.00011 | $0.00363 |
| Haiku 4.5 | $0.00005 | $0.00181 |
Grade A, and why
cinematic-shot-prompt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematic Shot Prompt
What This Skill Does
Generates a film-grammar-aware Midjourney prompt from a scene description — specifying shot type, lens, lighting, color grade, and mood — that produces an image with the visual language of a cinematically composed film still.
When To Use This Skill
- You need a high-quality image that looks like a film still, not a stock photo or illustration
- You are art directing a project (documentary, editorial, series bible) and need reference images that convey a specific visual language
- You want to show a director, DP, or client what a scene or sequence should look and feel like
- You are building a mood board using AI-generated imagery and need precise control over the cinematic language
What You Need To Provide
Required: A description of the scene, subject, or moment you want to capture; the emotional mood or atmosphere the image should convey Optional: Reference films or cinematographers whose visual language you want to evoke; specific shot type (close-up, wide, overhead, etc.); time of day or lighting condition; color palette or grade preference; aspect ratio; Midjourney version (default is v6)
How the Assistant Approaches This
- Translates the scene description into precise cinematographic language — shot type (ECU, MCU, wide, aerial), lens choice (24mm wide, 85mm portrait, 200mm compressed telephoto), and camera position (eye-level, low angle, dutch tilt) — choosing the option that best serves the described mood
- Specifies the lighting setup using film industry terms (Rembrandt, hard side-light, golden hour, practical-only, overcast diffused) rather than generic descriptors ("nice light," "dramatic")
- Defines a color grade or palette (desaturated teal-and-orange, warm amber shadows, cold blue midtones, high-contrast monochrome) that supports the emotional register
- Adds cinematic texture parameters — grain, bokeh, depth of field — that signal "film still" to the model rather than "digital photography" or "illustration"
- Structures the final prompt in Midjourney's preferred order: subject, action/context, shot type, lens, lighting, color grade, mood, style parameters
- After the prompt(s), provides a "Next Step" note: paste the prompt into Midjourney, generate at least 4 initial variations before upscaling, and which parameter to adjust first if the output is too stylized or not cinematic enough (typically --s for stylization strength or --c for chaos)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 88 lines · 53 tokens per session scan A 568ba182fb10
cinematic-shot-prompt is a skill published in the GitHub repository ur-grue/autopunk-media-skills (32 stars, last pushed 12d ago), licensed MIT. It adds 53 tokens to every session and 1,814 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
xiaoyuzhou-podcast-notes
A workflow that turns a public Xiaoyuzhou FM podcast episode into structured Markdown notes and a saved transcript. Xiaoyuzhou FM is a Chinese podcast platform.
c-research
Summarize web URLs, PDFs, YouTube videos, and podcasts using the summarize CLI. Instantly extract key points from any content type without manual reading. Useful for research, link digests, and media review.
transcript-ingestion
Transcript ingestion authority — capture, normalize, and prioritize transcripts from YouTube videos, podcast pages, captions, show notes, and transcript-like page content for persona systems, RAG pipelines, and grounded synthesis.
youtube-seo-competitor
Advanced YouTube competitor intelligence. Detects direct competitors, extracts winning title/thumbnail/hook patterns from transcripts, infers retention strategies from pacing, correlates posting cadence with performance, and identifies format-market-fit gaps. Use when user says "YouTube competitor analysis", "what are…
youtube-seo-optimize
Advanced YouTube metadata optimizer. Generates Browse-primary and Search-primary title variants, entity-rich descriptions, tags, chapters with Key Moments schema, 15-second hook script, translated metadata for top markets, pinned comment, and end-screen plan. Use when user says "optimize my video", "rewrite my title"…
youtube-seo-video
Advanced single-video SEO analysis covering retention curve diagnosis, intro hook strength, APV vs niche benchmark, entity/semantic coverage, title/description/tags, chapters with Key Moments schema, thumbnail, captions, audio loudness, end-screens, and engagement signals. Use when user says "analyze this video", "why…